mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 10:35:01 +00:00
feat: add huggingface embeddings backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
94916749c5
commit
982a7e86a8
7 changed files with 529 additions and 8 deletions
100
api/api_test.go
100
api/api_test.go
|
@ -386,6 +386,102 @@ var _ = Describe("API test", func() {
|
|||
})
|
||||
})
|
||||
|
||||
Context("External gRPCs", func() {
|
||||
BeforeEach(func() {
|
||||
modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
|
||||
c, cancel = context.WithCancel(context.Background())
|
||||
|
||||
app, err := App(
|
||||
append(commonOpts,
|
||||
options.WithContext(c),
|
||||
options.WithAudioDir(tmpdir),
|
||||
options.WithImageDir(tmpdir),
|
||||
options.WithModelLoader(modelLoader),
|
||||
options.WithBackendAssets(backendAssets),
|
||||
options.WithExternalBackend("huggingface", os.Getenv("HUGGINGFACE_GRPC")),
|
||||
options.WithBackendAssetsOutput(tmpdir))...,
|
||||
)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
go app.Listen("127.0.0.1:9090")
|
||||
|
||||
defaultConfig := openai.DefaultConfig("")
|
||||
defaultConfig.BaseURL = "http://127.0.0.1:9090/v1"
|
||||
|
||||
// Wait for API to be ready
|
||||
client = openai.NewClientWithConfig(defaultConfig)
|
||||
Eventually(func() error {
|
||||
_, err := client.ListModels(context.TODO())
|
||||
return err
|
||||
}, "2m").ShouldNot(HaveOccurred())
|
||||
})
|
||||
|
||||
AfterEach(func() {
|
||||
cancel()
|
||||
app.Shutdown()
|
||||
os.RemoveAll(tmpdir)
|
||||
})
|
||||
|
||||
Context("API query", func() {
|
||||
BeforeEach(func() {
|
||||
modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
|
||||
c, cancel = context.WithCancel(context.Background())
|
||||
|
||||
var err error
|
||||
app, err = App(
|
||||
append(commonOpts,
|
||||
options.WithDebug(true),
|
||||
options.WithContext(c), options.WithModelLoader(modelLoader))...)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
go app.Listen("127.0.0.1:9090")
|
||||
|
||||
defaultConfig := openai.DefaultConfig("")
|
||||
defaultConfig.BaseURL = "http://127.0.0.1:9090/v1"
|
||||
|
||||
client2 = openaigo.NewClient("")
|
||||
client2.BaseURL = defaultConfig.BaseURL
|
||||
|
||||
// Wait for API to be ready
|
||||
client = openai.NewClientWithConfig(defaultConfig)
|
||||
Eventually(func() error {
|
||||
_, err := client.ListModels(context.TODO())
|
||||
return err
|
||||
}, "2m").ShouldNot(HaveOccurred())
|
||||
})
|
||||
AfterEach(func() {
|
||||
cancel()
|
||||
app.Shutdown()
|
||||
})
|
||||
|
||||
It("calculate embeddings with huggingface", func() {
|
||||
if runtime.GOOS != "linux" {
|
||||
Skip("test supported only on linux")
|
||||
}
|
||||
resp, err := client.CreateEmbeddings(
|
||||
context.Background(),
|
||||
openai.EmbeddingRequest{
|
||||
Model: openai.AdaCodeSearchCode,
|
||||
Input: []string{"sun", "cat"},
|
||||
},
|
||||
)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 384))
|
||||
Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 384))
|
||||
|
||||
sunEmbedding := resp.Data[0].Embedding
|
||||
resp2, err := client.CreateEmbeddings(
|
||||
context.Background(),
|
||||
openai.EmbeddingRequest{
|
||||
Model: openai.AdaCodeSearchCode,
|
||||
Input: []string{"sun"},
|
||||
},
|
||||
)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(resp2.Data[0].Embedding).To(Equal(sunEmbedding))
|
||||
Expect(resp2.Data[0].Embedding).ToNot(Equal(resp.Data[1].Embedding))
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
Context("Model gallery", func() {
|
||||
BeforeEach(func() {
|
||||
var err error
|
||||
|
@ -530,7 +626,7 @@ var _ = Describe("API test", func() {
|
|||
It("returns the models list", func() {
|
||||
models, err := client.ListModels(context.TODO())
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(models.Models)).To(Equal(10))
|
||||
Expect(len(models.Models)).To(Equal(11))
|
||||
})
|
||||
It("can generate completions", func() {
|
||||
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "testmodel", Prompt: "abcdedfghikl"})
|
||||
|
@ -707,7 +803,7 @@ var _ = Describe("API test", func() {
|
|||
It("can generate chat completions from config file", func() {
|
||||
models, err := client.ListModels(context.TODO())
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(models.Models)).To(Equal(12))
|
||||
Expect(len(models.Models)).To(Equal(13))
|
||||
})
|
||||
It("can generate chat completions from config file", func() {
|
||||
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list1", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "abcdedfghikl"}}})
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue